SANTA CLARA, CA, Oct 28, 2010 (MARKETWIRE via COMTEX) --
Tianhe-1A, a new supercomputer revealed today at HPC 2010 China,has set a new performance record of 2.507 petaflops, as measured bythe LINPACK benchmark, making it the fastest system in China and inthe world today(1).
Tianhe-1A epitomizes modern heterogeneous computing by couplingmassively parallel GPUs with multi-core CPUs, enabling significantachievements in performance, size and power. The system uses 7,168NVIDIA(R) Tesla(TM) M2050 GPUs and 14,336 CPUs; it would require morethan 50,000 CPUs and twice as much floor space to deliver the sameperformance using CPUs alone.
More importantly, a 2.507 petaflop system built entirely with CPUswould consume more than 12 megawatts. Thanks to the use of GPUs in aheterogeneous computing environment, Tianhe-1A consumes only 4.04megawatts, making it 3 times more power efficient -- the differencein power consumption is enough to provide electricity to over 5000homes for a year.
Tianhe-1A was designed by the National University of DefenseTechnology (NUDT) in China. The system is housed at NationalSupercomputer Center in Tianjin and is already fully operational.
"The performance and efficiency of Tianhe-1A was simply not possiblewithout GPUs," said Guangming Liu, chief of National SupercomputerCenter in Tianjin. "The scientific research that is now possible witha system of this scale is almost without limits; we could not be morepleased with the results."
The Tianhe-1A supercomputer will be operated as an open access systemto use for large scale scientific computations.
"GPUs are redefining high performance computing," said Jen-HsunHuang, president and CEO of NVIDIA. "With the Tianhe-1A, GPUs nowpower two of the top three fastest computers in the world today.These GPU supercomputers are essential tools for scientists lookingto turbocharge their rate of discovery."
NVIDIA Tesla GPUs, based on the CUDA(TM) parallel computingarchitecture, are designed specifically for high performancecomputing (HPC) environments and deliver transformative performanceincreases across a wide range of HPC fields, including drugdiscovery, hurricane and tsunami modeling, cancer research, cardesign, even studying the formation of galaxies.
For more information on NVIDIA Tesla high performance GPU computingproducts, go here
About NVIDIA NVIDIA (NASDAQ: NVDA) awakened the world to the powerof computer graphics when it invented the GPU in 1999. Since then, ithas consistently set new standards in visual computing withbreathtaking, interactive graphics available on devices ranging fromtablets and portable media players to notebooks and workstations.NVIDIA's expertise in programmable GPUs has led to breakthroughs inparallel processing which make supercomputing inexpensive and widelyaccessible. The Company holds more than 1,600 patents worldwide,including ones covering designs and insights that are essential tomodern computing. For more information, see www.nvidia.com.
Certain statements in this press release including, but not limitedto, statements as to: the benefits and impact of NVIDIA Tesla GPUs,based on the CUDA parallel computing architecture; and the impact ofthe company's patents on modern computing are forward-lookingstatements that are subject to risks and uncertainties that couldcause results to be materially different than expectations. Importantfactors that could cause actual results to differ materially include:global economic conditions; our reliance on third parties tomanufacture, assemble, package and test our products; the impact oftechnological development and competition; development of faster ormore efficient technology; design, manufacturing or software defects;changes in consumer preferences or demands; changes in industrystandards and interfaces; unexpected loss of performance of ourproducts or technologies when integrated into systems; as well asother factors detailed from time to time in the reports NVIDIA fileswith the Securities and Exchange Commission, or SEC, including itsForm 10-Q for the fiscal period ended August 1, 2010. Copies ofreports filed with the SEC are posted on the company's website andare available from NVIDIA without charge. These forward-lookingstatements are not guarantees of future performance and speak only asof the date hereof, and, except as required by law, NVIDIA disclaimsany obligation to update these forward-looking statements to reflectfuture events or circumstances.
Copyright 2010 NVIDIA Corporation. All rights reserved. NVIDIA, theNVIDIA logo, Tesla, and CUDA, are trademarks and/or registeredtrademarks of NVIDIA Corporation in the U.S. and other countries.Other company and product names may be trademarks of the respectivecompanies with which they are associated. Features, pricing,availability, and specifications are subject to change withoutnotice.
(1) As compared to performance data submitted for the June 2010Top500 list
